Erste Schritte (AWS SDK for Python (Boto3))

Das folgende Programm ist ein Beispiel für die Verwendung Amazon Kendra in einem Python-Programm. Das Programm führt die folgenden Aktionen aus:

1. Erstellt mithilfe der CreateIndexOperation einen neuen Index.

2. Wartet auf den Abschluss der Indexerstellung. Es verwendet den DescribeIndexVorgang, um den Status des Indexes zu überwachen.

3. Sobald der Index aktiv ist, erstellt er mithilfe der CreateDataSourceOperation eine Datenquelle.

4. Wartet, bis die Erstellung der Datenquelle abgeschlossen ist. Es verwendet den DescribeDataSourceVorgang, um den Status der Datenquelle zu überwachen.

5. Wenn die Datenquelle aktiv ist, synchronisiert sie den Index mithilfe der StartDataSourceSyncJobOperation mit dem Inhalt der Datenquelle.

import boto3
from botocore.exceptions import ClientError
import pprint
import time

kendra = boto3.client("kendra")

print("Create an index.")

# Provide a name for the index
index_name = "python-getting-started-index"
# Provide an optional decription for the index
description = "Getting started index"
# Provide the IAM role ARN required for indexes
index_role_arn = "arn:aws:iam::${accountId}:role/KendraRoleForGettingStartedIndex"

try:
    index_response = kendra.create_index(
        Description = description,
        Name = index_name,
        RoleArn = index_role_arn
    )

    pprint.pprint(index_response)

    index_id = index_response["Id"]

    print("Wait for Amazon Kendra to create the index.")

    while True:
        # Get the details of the index, such as the status
        index_description = kendra.describe_index(
            Id = index_id
        )
        # When status is not CREATING quit.
        status = index_description["Status"]
        print(" Creating index. Status: "+status)
        time.sleep(60)
        if status != "CREATING":
            break

    print("Create an S3 data source.")
    
    # Provide a name for the data source
    data_source_name = "python-getting-started-data-source"
    # Provide an optional description for the data source
    data_source_description = "Getting started data source."
    # Provide the IAM role ARN required for data sources
    data_source_role_arn = "arn:aws:iam::${accountId}:role/KendraRoleForGettingStartedDataSource"
    # Provide the data source connection information 
    S3_bucket_name = "S3-bucket-name"
    data_source_type = "S3"
    # Configure the data source
    configuration = {"S3Configuration":
        {
            "BucketName": S3_bucket_name
        }
    }
    
    """
    If you connect to your data source using a template schema, 
    configure the template schema
    configuration = {"TemplateConfiguration":
        {
            "Template": {JSON schema}
        }
    }
    """
    
    data_source_response = kendra.create_data_source(
        Name = data_source_name,
        Description = data_source_name,
        RoleArn = data_source_role_arn,
        Type = data_source_type,
        Configuration = configuration,
        IndexId = index_id
    )

    pprint.pprint(data_source_response)

    data_source_id = data_source_response["Id"]

    print("Wait for Amazon Kendra to create the data source.")

    while True:
        # Get the details of the data source, such as the status
        data_source_description = kendra.describe_data_source(
            Id = data_source_id,
            IndexId = index_id
        )
        # If status is not CREATING, then quit
        status = data_source_description["Status"]
        print(" Creating data source. Status: "+status)
        time.sleep(60)
        if status != "CREATING":
            break

    print("Synchronize the data source.")

    sync_response = kendra.start_data_source_sync_job(
        Id = data_source_id,
        IndexId = index_id
    )

    pprint.pprint(sync_response)

    print("Wait for the data source to sync with the index.")

    while True:

        jobs = kendra.list_data_source_sync_jobs(
            Id = data_source_id,
            IndexId = index_id
        )

        # For this example, there should be one job
        status = jobs["History"][0]["Status"]

        print(" Syncing data source. Status: "+status)
        if status != "SYNCING":
            break
        time.sleep(60)

except  ClientError as e:
        print("%s" % e)

print("Program ends.")